1. Vacatures
  2. Universiteit van Amsterdam (UvA)
  3. Postdoctoral researcher on reinforcement learning with structured data

Helaas, deze vacature staat inmiddels niet meer online

Kijk gerust verder naar andere vacatures.

Postdoctoral researcher on reinforcement learning with structured data

Are you not afraid to apply (deep) reinforcement learning techniques on a mix of structured and unstructured data? We are looking for a postdoctoral …

ongeveer een maand geleden


Science Park, Amsterdam, Noord-Holland
Vast contract
Uren per week:
38 - 38 uur
€ 2790 - € 4402 per maand


Are you not afraid to apply (deep) reinforcement learning techniques on a mix of structured and unstructured data? We are looking for a postdoctoral researcher interested in performing research on developing (deep) reinforcement learning techniques that can take structured data such as graphs, sequences, and lists as input or output data.

In the application domain of providing recommendations to users, input data is often strongly structured and multi-modal (knowledge graphs describing uses and items, complex interaction histories of the users, etcetera). Instead of providing a single or multiple recommendations, we might also want to give a more structured output, think of a list of articles that can be read in order to understand a complex topic, or a conditional plan: try reading X, but if it's too complex, go for Y instead. In this position, your challenge will be to develop architectures and algorithms for neural models that allow taking in structured and multi-modal information such as user context, text, and a knowledge graph, and output structured recommendations; optimising such models from trial-and-error using reinforcement learning techniques.

The research will place within the Discovery lab. This lab is a collaboration between the University of Amsterdam, the Vrije Universiteit Amsterdam, and Elsevier. Our philosophy is to drive scientific discovery using machine intelligence. Our goal is to study and develop technology, infrastructure and methods to support the current transformation of science, specifically regarding data-driven activity, where scientists increasingly rely on intelligent tooling for searching and reading scientific literature, to formulate hypotheses, and to interpret data.

Researchers in this lab can conduct academic research at the university, and apply their findings with real world data and systems. This particular position is associated with the Amsterdam Machine Learning Lab (AMLAB). The Discovery Lab is also closely integrated with the INtelligent Data Engineering Lab (INDE Lab), the information and language processing systems group (ILPS) , and the Knowledge Representation and Reasoning group. We are also embedded within the Amsterdam data science and artificial intelligence ecosystem (e.g. Amsterdam Data Science and Innovation Center for Artificial Intelligence) and value practice-informed and interdisciplinary research and outreach. 

We strongly encourage applications coming from a unique perspective. Tell us how your background fits with the aims of the lab.

What are you going to do?

You are expected to:

  • invent, evaluate and describe novel architectures and algorithms for (deep) reinforcement learning with structured data;
  • integrate and evaluate such algorithms in experimental scenarios, including applications in recommender systems;
  • present research results at international conferences, workshops, and journals;
  • become an active member of the research community and to collaborate with other researchers, both within and outside the Informatics Institute and the Discovery Lab;
  • spend about 40% of your time working on your research projects from the Discovery lab space at the Elsevier office in Amsterdam;
  • show independence in achieving research goals and collaborating with PhD students and researchers;
  • contribute to teaching activities, such as lectures, lab courses, or supervising bachelor and master students.


  • A PhD degree in Artificial Intelligence, Machine Learning or a closely related field;
  • a strong scientific and mathematical background in artificial intelligence. Familiarity and interests with reinforcement learning is preferable;
  • a good academic record and eagerness to tackle complex scientific problems;
  • a record of publishing in relevant high-quality conferences or journals in the above fields;
  • strong programming skills, e.g. in Python, Java, Scala, C++. Preferably, you have experience with Python deep learning toolboxes;
  • the ability to work well in teams and communicate fluently in written and spoken English;
  • the ability to invent and evaluate novel algorithms and present these orally and in writing.


Our offer

A temporary contract for 38 hours per week for the duration of 12 months. After positive evaluation, the contract will be extended with 36 months.

The salary, depending on relevant experience before the beginning of the employment contract, will be €2,790 to €4,402 (scale 10) gross per month, based on a full-time contract of 38 hours a week. This isexclusive 8 % holiday allowance and 8.3% end-of-year bonus. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Dutch Universities is applicable.

Are you curious about our extensive package of secondary employment benefits like our excellent opportunities for study and development? Take a look here.

Additional information

Do you have questions about this vacancy? Or do you want to know more about our organisation? Please contact:

Applications should not be send through email, but submitted through the button in the right corner of this advertisement.